Nonlinear Meta-Learning Can Guarantee Faster Rates

Understand

Many recent theoretical works on \emph{meta-learning} aim to achieve guarantees in leveraging similar representational structures from related tasks towards simplifying a target task.

• The main aim of theoretical guarantees on the subject is to establish the extent to which convergence rates -- in learning a common representation -- \emph{may scale with the number $N$ of tasks} (as well as the number of samples per task).
• First steps in this setting demonstrate this property when both the shared representation amongst tasks, and task-specific regression functions, are linear.
• This linear setting readily reveals the benefits of aggregating tasks, e.g., via averaging arguments.